Contribution to the estimation of the speech message from the corrupted signal with noise

In this article the method of Kalman and Bucy filter is used for the estimation of the speech message from the corrupted signal with noise. In this case we must know the statistic properties of the speech message and the statistic properties of the noise. The statistic properties of the speech message are taken from power spectral density of the mean speech, but the disturbing noise is described by the statistic of the white noise. Then the mathematical model of the filter is shown with its simulation on the analog computer.